Artificial Intelligence in Agriculture最新文献_第2页

Prediction of wheat stem biomass using a new unified model driven by phenological variable under remote-sensed canopy vegetation index constraints 遥感冠层植被指数约束下物候变量驱动的小麦茎生物量统一预测模型

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-22 DOI: 10.1016/j.aiia.2025.11.007

Weinan Chen , Guijun Yang , Yang Meng , Haikuan Feng , Hongrui Wen , Aohua Tang , Jing Zhang , Hao Yang , Heli Li , Xingang Xu , Changchun Li , Zhenhong Li

Timely and accurate prediction of stem dry biomass (SDB) is crucial for monitoring crop growing status. However, conventional biomass estimation models are often limited by the influence of crop growth phase, which significantly restricts their temporal and spatial transferability. This study aimed to develop a semi-mechanistic stem biomass prediction model (PVWheat-SDB) using phenological variable (PV) to accurately predict winter wheat SDB across different growth stages. The core of the model is to predict SDB using PV under remote-sensed canopy vegetation indices (VIs) constraint. The results demonstrated that VIs can quantify the variations in stem growth equations under different planting conditions and varieties. The developed a PVWheat-SDB model using normalized difference red edge (NDRE) and accumulated growing degree days (AGDD) performed well for SDB predictions, with R², RMSE, nRMSE and MAE values of 0.88, 75.48 g/m², 8.04 % and 55.36 g/m² for the validation datasets of field spectral reflectance, and 0.82, 81.76 g/m², 11.22 % and 62.82 g/m² when transferred to unmanned aerial vehicle (UAV) hyperspectral images. Furthermore, the model can not only estimate SDB at the current growth stage, but also predict SDB of subsequent phenological stages. The growth stage stacking strategy indicated that the model accuracy improves significantly as more growth stages are incorporated, especially during the reproductive stages. These results all highlight the robustness and transferability of the PVWheat-SDB model in accurately predicting SDB across different growing seasons and growth stages.

及时准确地预测茎干生物量对监测作物生长状况至关重要。然而，传统的生物量估算模型往往受到作物生长阶段的影响，这严重限制了其时空可移植性。本研究旨在利用物候变量（PV）建立半机械性的冬小麦茎生物量预测模型（PVWheat-SDB），以准确预测冬小麦不同生育期的茎生物量。该模型的核心是在遥感冠层植被指数（VIs）约束下利用PV预测深发展。结果表明，VIs可以量化不同种植条件和品种下茎秆生长方程的变化。利用归一化差分红边（NDRE）和累积生长度数（AGDD）建立pv小麦-SDB模型，对田间光谱反射率验证数据集的R2、RMSE、nRMSE和MAE值分别为0.88、75.48 g/m2、8.04%和55.36 g/m2，对无人机高光谱图像的预测值分别为0.82、81.76 g/m2、11.22%和62.82 g/m2。此外，该模型不仅可以预测当前生长阶段的深发展，还可以预测后续物候阶段的深发展。生长期叠加策略表明，随着生长期的增加，模型精度显著提高，尤其是在繁殖期。这些结果都突出了PVWheat-SDB模型在准确预测不同生长季节和生长阶段SDB方面的稳健性和可移植性。

{"title":"Prediction of wheat stem biomass using a new unified model driven by phenological variable under remote-sensed canopy vegetation index constraints","authors":"Weinan Chen , Guijun Yang , Yang Meng , Haikuan Feng , Hongrui Wen , Aohua Tang , Jing Zhang , Hao Yang , Heli Li , Xingang Xu , Changchun Li , Zhenhong Li","doi":"10.1016/j.aiia.2025.11.007","DOIUrl":"10.1016/j.aiia.2025.11.007","url":null,"abstract":"<div><div>Timely and accurate prediction of stem dry biomass (SDB) is crucial for monitoring crop growing status. However, conventional biomass estimation models are often limited by the influence of crop growth phase, which significantly restricts their temporal and spatial transferability. This study aimed to develop a semi-mechanistic stem biomass prediction model (PVWheat-SDB) using phenological variable (PV) to accurately predict winter wheat SDB across different growth stages. The core of the model is to predict SDB using PV under remote-sensed canopy vegetation indices (VIs) constraint. The results demonstrated that VIs can quantify the variations in stem growth equations under different planting conditions and varieties. The developed a PVWheat-SDB model using normalized difference red edge (NDRE) and accumulated growing degree days (AGDD) performed well for SDB predictions, with R<sup>2</sup>, RMSE, nRMSE and MAE values of 0.88, 75.48 g/m<sup>2</sup>, 8.04 % and 55.36 g/m<sup>2</sup> for the validation datasets of field spectral reflectance, and 0.82, 81.76 g/m<sup>2</sup>, 11.22 % and 62.82 g/m<sup>2</sup> when transferred to unmanned aerial vehicle (UAV) hyperspectral images. Furthermore, the model can not only estimate SDB at the current growth stage, but also predict SDB of subsequent phenological stages. The growth stage stacking strategy indicated that the model accuracy improves significantly as more growth stages are incorporated, especially during the reproductive stages. These results all highlight the robustness and transferability of the PVWheat-SDB model in accurately predicting SDB across different growing seasons and growth stages.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 658-671"},"PeriodicalIF":12.4,"publicationDate":"2025-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145924151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale feature alignment network for 19-class semantic segmentation in agricultural environments 农业环境下19类语义分割的多尺度特征对齐网络

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-22 DOI: 10.1016/j.aiia.2025.11.008

Zhi-xin Yao , Hao Wang , Zhi-jun Meng , Liang-liang Yang , Tai-hong Zhang

To improve environmental perception and ensure reliable agricultural machinery navigation during field transitions under unstructured farm road conditions, this study utilizes high-resolution RGB camera vision navigation technology to propose a Multi-Scale Feature Alignment Network (MSFA-Net) for 19-class semantic segmentation of agricultural environment, which includes information such as roads, pedestrians, and vehicles. MSFA-Net introduces two key innovations: the DASP module, which integrates multi-scale feature extraction with dual attention mechanisms (spatial and channel), and the MSFA architecture, which enables robust boundary extraction and mitigates interference from lighting variations and obstacles like vegetation. Compared to existing models, MSFA-Net uniquely combines efficient multi-scale feature extraction with real-time inference capabilities, achieving an mIoU of 84.46 % and an mPA of 96.10 %. For 512 × 512 input images, the model processes an average of 26 images/s on a GTX 1650Ti, with a boundary extraction error of less than 0.47 m within 20 m. These results indicate that the proposed MSFA-Net can significantly reduce navigation errors and improve the perception stability of agricultural machinery during field operations. Furthermore, the model can be exported to ONNX or TensorFlow Lite formats, facilitating efficient deployment on embedded devices and existing farm navigation systems.

为了提高农业机械在非结构化农田道路条件下的环境感知能力，保证农机导航的可靠性，本研究利用高分辨率RGB相机视觉导航技术，提出了一种多尺度特征对齐网络（MSFA-Net），对包括道路、行人、车辆等信息在内的农业环境进行19类语义分割。MSFA- net引入了两个关键的创新：DASP模块，它集成了具有双重注意机制（空间和通道）的多尺度特征提取；MSFA架构，它可以实现鲁棒的边界提取，并减轻光照变化和植被等障碍物的干扰。与现有模型相比，MSFA-Net独特地将高效的多尺度特征提取与实时推理能力相结合，实现了84.46%的mIoU和96.10%的mPA。对于512 × 512的输入图像，该模型在GTX 1650Ti上平均处理26张图像/s，在20 m范围内边界提取误差小于0.47 m。结果表明，本文提出的MSFA-Net能够显著降低导航误差，提高农机在野外作业中的感知稳定性。此外，该模型可以导出为ONNX或TensorFlow Lite格式，便于在嵌入式设备和现有农场导航系统上进行有效部署。

{"title":"Multi-scale feature alignment network for 19-class semantic segmentation in agricultural environments","authors":"Zhi-xin Yao , Hao Wang , Zhi-jun Meng , Liang-liang Yang , Tai-hong Zhang","doi":"10.1016/j.aiia.2025.11.008","DOIUrl":"10.1016/j.aiia.2025.11.008","url":null,"abstract":"<div><div>To improve environmental perception and ensure reliable agricultural machinery navigation during field transitions under unstructured farm road conditions, this study utilizes high-resolution RGB camera vision navigation technology to propose a Multi-Scale Feature Alignment Network (MSFA-Net) for 19-class semantic segmentation of agricultural environment, which includes information such as roads, pedestrians, and vehicles. MSFA-Net introduces two key innovations: the DASP module, which integrates multi-scale feature extraction with dual attention mechanisms (spatial and channel), and the MSFA architecture, which enables robust boundary extraction and mitigates interference from lighting variations and obstacles like vegetation. Compared to existing models, MSFA-Net uniquely combines efficient multi-scale feature extraction with real-time inference capabilities, achieving an mIoU of 84.46 % and an mPA of 96.10 %. For 512 × 512 input images, the model processes an average of 26 images/s on a GTX 1650Ti, with a boundary extraction error of less than 0.47 m within 20 m. These results indicate that the proposed MSFA-Net can significantly reduce navigation errors and improve the perception stability of agricultural machinery during field operations. Furthermore, the model can be exported to ONNX or TensorFlow Lite formats, facilitating efficient deployment on embedded devices and existing farm navigation systems.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 529-545"},"PeriodicalIF":12.4,"publicationDate":"2025-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual attention guided context-aware feature learning for residual unfilled grains detection on threshed rice panicles 双重注意引导的上下文感知特征学习在脱粒水稻穗部残留未填充粒检测中的应用

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-15 DOI: 10.1016/j.aiia.2025.11.005

Yuhao Zhou , Xiao Feng , Shuqi Tang , Jinpeng Yang , Shaobin Chen , Xiangbao Meng , Zhanpeng Liang , Ruijun Ma , Long Qi

Accurate detection of residual unfilled grains on threshed rice panicles is a critical step in determining a reliable grain-setting rate, and holds significant potential for the development of high-quality rice strains. Recent deep learning-based techniques have been actively explored for discerning various types of objects. However, this detection task is challenging, as many objects are densely occluded by branches or other unfilled grains. Additionally, some unfilled grains are closely adjacent and exhibit small sizes, further complicating the detection process. To address these challenges, this paper proposes a novel Channel-global Spatial-local Dual Attention (CSDA) module, aimed at enhancing feature correlation learning and contextual information embedding. Specifically, the channel- and spatial-wise attention are deployed on two parallel branches, and incorporated with the global and local representation learning paradigm, respectively. Furthermore, we integrate the CSDA module with the backbone of an object detector, and refine the loss function and detection head using the Focaler-SIoU and tiny object prediction head. This enables the object detector to effectively differentiate residual unfilled grains from occlusions, and at the meantime, focusing on the subtle differences between closely adjacent and small-sized unfilled grains. Experimental results show that our work achieves superior detection performance versus other competitors with an [email protected] of 95.3 % (outperforming rivals by 1.5–32.6 %) and a frame rate of 154 FPS (outperforming rivals by 12–132 FPS), enjoying substantial potentials for practical applications.

准确检测脱粒后稻穗上的剩余未灌浆粒是确定可靠的结实率的关键步骤，对开发优质水稻品系具有重要的潜力。最近基于深度学习的技术已经被积极地用于识别各种类型的物体。然而，这种检测任务具有挑战性，因为许多物体被树枝或其他未填充的颗粒密集地遮挡。此外，一些未填充的颗粒紧密相邻且尺寸较小，进一步使检测过程复杂化。为了解决这些问题，本文提出了一种新的通道-全局空间-局部双重注意（CSDA）模块，旨在增强特征相关学习和上下文信息嵌入。具体来说，渠道和空间智慧的注意力被部署在两个平行的分支上，并分别与全局和局部表征学习范式相结合。此外，我们将CSDA模块与目标检测器的主干集成，并使用Focaler-SIoU和微小目标预测头来改进损失函数和检测头。这使得目标检测器能够有效地区分残差未填充颗粒和遮挡物，同时，能够专注于相邻颗粒和小尺寸未填充颗粒之间的细微差异。实验结果表明，我们的工作取得了优于其他竞争对手的检测性能，[email protected]的检测率为95.3%（优于竞争对手1.5 - 32.6%），帧率为154 FPS（优于竞争对手12-132 FPS），具有很大的实际应用潜力。

{"title":"Dual attention guided context-aware feature learning for residual unfilled grains detection on threshed rice panicles","authors":"Yuhao Zhou , Xiao Feng , Shuqi Tang , Jinpeng Yang , Shaobin Chen , Xiangbao Meng , Zhanpeng Liang , Ruijun Ma , Long Qi","doi":"10.1016/j.aiia.2025.11.005","DOIUrl":"10.1016/j.aiia.2025.11.005","url":null,"abstract":"<div><div>Accurate detection of residual unfilled grains on threshed rice panicles is a critical step in determining a reliable grain-setting rate, and holds significant potential for the development of high-quality rice strains. Recent deep learning-based techniques have been actively explored for discerning various types of objects. However, this detection task is challenging, as many objects are densely occluded by branches or other unfilled grains. Additionally, some unfilled grains are closely adjacent and exhibit small sizes, further complicating the detection process. To address these challenges, this paper proposes a novel Channel-global Spatial-local Dual Attention (CSDA) module, aimed at enhancing feature correlation learning and contextual information embedding. Specifically, the channel- and spatial-wise attention are deployed on two parallel branches, and incorporated with the global and local representation learning paradigm, respectively. Furthermore, we integrate the CSDA module with the backbone of an object detector, and refine the loss function and detection head using the Focaler-SIoU and tiny object prediction head. This enables the object detector to effectively differentiate residual unfilled grains from occlusions, and at the meantime, focusing on the subtle differences between closely adjacent and small-sized unfilled grains. Experimental results show that our work achieves superior detection performance versus other competitors with an [email protected] of 95.3 % (outperforming rivals by 1.5–32.6 %) and a frame rate of 154 FPS (outperforming rivals by 12–132 FPS), enjoying substantial potentials for practical applications.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 514-528"},"PeriodicalIF":12.4,"publicationDate":"2025-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advancing lightweight and efficient detection of tomato main stems for edge device deployment 推进番茄主茎的轻量化和高效检测，用于边缘设备部署

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-10 DOI: 10.1016/j.aiia.2025.10.016

Guohua Gao, Lifa Fang, Zihua Zhang, Jiahao Li

Automated pruning and defoliation of tomato plants are essential in modern cultivation systems for optimizing canopy structure, enhancing air circulation, and increasing yield. However, detecting main stems in the field faces significant challenges, like complex background interference, limited field of view, dense foliage occlusion, and curved stems. To address those challenges while ensuring hardware friendliness, computational efficiency, and real-time response, this study proposes a lightweight tomato main stem detection, optimisation, and deployment scheme. First, an efficient semi-automatic rotated bounding box annotation strategy is employed to segment the visible main stem segments, thus improving the adaptability to curved stems. Second, the lightweight network, YOLOR-Slim, is constructed to significantly reduce model complexity while maintaining detection performance through automated iterative pruning at the group-level of channel importance and a hybrid feature-based and logic-based knowledge distillation mechanism. Finally, an efficient and real-time main stem detection is achieved by deploying the model on inference engines and embedded platforms with various types and quantization bits. Experimental results showed that YOLOR-Slim achieved 87.5 % mAP@50, 1.9G Flops, 1.4 M parameters, and 7.4 ms inference time (pre-processing, inference, and post-processing) on the workstation, representing reductions of 2.8 %, 10.0 M, and 27.5G compared to the original model. After conversion with TensorRT, the inference time on Jetson Nano reached 57.6 ms, validating the operational efficiency and deployment applicability on edge devices. The YOLOR-Slim strikes a balance between inference speed, computational resources usage, and detection accuracy, providing a reliable perceptual foundation for automated pruning tasks in precision agriculture.

番茄植株的自动修剪和落叶在现代栽培系统中是优化树冠结构、促进空气流通和提高产量所必需的。然而，在野外检测主茎面临着复杂的背景干扰、有限的视野、茂密的树叶遮挡和弯曲的茎等重大挑战。为了应对这些挑战，同时确保硬件友好性、计算效率和实时响应，本研究提出了一种轻量级番茄主茎检测、优化和部署方案。首先，采用高效的半自动旋转包围框标注策略对可见的主茎段进行分割，提高了对弯曲茎的适应性；其次，构建轻量级网络yolo - slim，通过通道重要性组级的自动迭代剪枝和基于特征和基于逻辑的混合知识蒸馏机制，在保持检测性能的同时显著降低模型复杂性。最后，将该模型部署在推理引擎和具有各种类型和量化位的嵌入式平台上，实现了高效实时的主干检测。实验结果表明，yolo - slim在工作站上实现了87.5% mAP@50, 1.9G Flops， 1.4 M参数和7.4 ms推理时间（预处理，推理和后处理），与原始模型相比减少了2.8%，10.0 M和27.5G。经过TensorRT转换后，Jetson Nano上的推理时间达到57.6 ms，验证了在边缘设备上的运行效率和部署适用性。yolo - slim在推理速度、计算资源使用和检测精度之间取得了平衡，为精准农业中的自动修剪任务提供了可靠的感知基础。

{"title":"Advancing lightweight and efficient detection of tomato main stems for edge device deployment","authors":"Guohua Gao, Lifa Fang, Zihua Zhang, Jiahao Li","doi":"10.1016/j.aiia.2025.10.016","DOIUrl":"10.1016/j.aiia.2025.10.016","url":null,"abstract":"<div><div>Automated pruning and defoliation of tomato plants are essential in modern cultivation systems for optimizing canopy structure, enhancing air circulation, and increasing yield. However, detecting main stems in the field faces significant challenges, like complex background interference, limited field of view, dense foliage occlusion, and curved stems. To address those challenges while ensuring hardware friendliness, computational efficiency, and real-time response, this study proposes a lightweight tomato main stem detection, optimisation, and deployment scheme. First, an efficient semi-automatic rotated bounding box annotation strategy is employed to segment the visible main stem segments, thus improving the adaptability to curved stems. Second, the lightweight network, YOLOR-Slim, is constructed to significantly reduce model complexity while maintaining detection performance through automated iterative pruning at the group-level of channel importance and a hybrid feature-based and logic-based knowledge distillation mechanism. Finally, an efficient and real-time main stem detection is achieved by deploying the model on inference engines and embedded platforms with various types and quantization bits. Experimental results showed that YOLOR-Slim achieved 87.5 % mAP@50, 1.9G Flops, 1.4 M parameters, and 7.4 ms inference time (pre-processing, inference, and post-processing) on the workstation, representing reductions of 2.8 %, 10.0 M, and 27.5G compared to the original model. After conversion with TensorRT, the inference time on Jetson Nano reached 57.6 ms, validating the operational efficiency and deployment applicability on edge devices. The YOLOR-Slim strikes a balance between inference speed, computational resources usage, and detection accuracy, providing a reliable perceptual foundation for automated pruning tasks in precision agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 458-479"},"PeriodicalIF":12.4,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-saving and stability-enhancing control for unmanned distributed drive electric plant protection vehicle based on active torque distribution 基于主动转矩分配的无人分布式驱动电动植保车节能增稳控制

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-05 DOI: 10.1016/j.aiia.2025.11.004

Wenxiang Xu , Yejun Zhu , Maohua Xiao , Mengnan Liu , Liling Ye , Yanpeng Yang , Ze Liu

The distributed drive electric plant protection vehicle (DDEPPV), equipped with a unique four-wheel independent drive system, demonstrates excellent path-tracking capability and dynamic performance in agricultural environments. However, during actual field operations, issues such as severe tire slip, poor driving stability, high rollover risk, and excessive energy consumption often arise due to improper torque distribution. This study proposes an energy-efficient and stability-enhancing control method based on active torque distribution, aiming to improve both operational safety and system efficiency. A hierarchical control architecture is adopted: the upper-level controller employs a nonlinear model predictive control (NMPC) to achieve coordinated control of steering and yaw moment, enhancing lateral stability and ensuring operational safety. The lower-level controller implements a direct torque allocation method based on an adaptive-weight multi-objective twin delayed deep deterministic policy gradient (AW-MO-TD3) algorithm, enabling joint optimization of tire slip ratio and energy consumption. Real-vehicle tests were conducted under two typical field conditions, and the results show that compared with conventional methods, the proposed strategy significantly improves key performance metrics including tracking accuracy, vehicle stability, and energy efficiency. Specifically, stability was enhanced by 29.1 % and 41.4 %, while energy consumption was reduced by 19.8 % and 21.1 % under dry plowed terrain and muddy rice field conditions, respectively. This research provides technical support for the intelligent control of distributed drive electric agricultural vehicles.

分布式驱动电动植保车（DDEPPV）采用独特的四轮独立驱动系统，在农业环境中表现出优异的路径跟踪能力和动态性能。然而，在实际的现场作业中，由于扭矩分配不当，往往会出现严重的轮胎打滑、行驶稳定性差、侧翻风险高、能耗过大等问题。本文提出了一种基于主动转矩分配的节能增稳控制方法，旨在提高运行安全性和系统效率。采用层次控制体系结构，上层控制器采用非线性模型预测控制（NMPC），实现转向力矩与偏航力矩的协调控制，增强横向稳定性，保证运行安全。底层控制器实现了基于自适应权值多目标双延迟深度确定性策略梯度（AW-MO-TD3）算法的直接转矩分配方法，实现了轮胎打滑率和能耗的联合优化。在两种典型的现场条件下进行了实车试验，结果表明，与传统方法相比，该策略显著提高了跟踪精度、车辆稳定性和能源效率等关键性能指标。旱耕地形和泥泞稻田条件下，稳定性分别提高29.1%和41.4%，能耗分别降低19.8%和21.1%。本研究为分布式驱动农用电动车辆的智能控制提供了技术支持。

{"title":"Energy-saving and stability-enhancing control for unmanned distributed drive electric plant protection vehicle based on active torque distribution","authors":"Wenxiang Xu , Yejun Zhu , Maohua Xiao , Mengnan Liu , Liling Ye , Yanpeng Yang , Ze Liu","doi":"10.1016/j.aiia.2025.11.004","DOIUrl":"10.1016/j.aiia.2025.11.004","url":null,"abstract":"<div><div>The distributed drive electric plant protection vehicle (DDEPPV), equipped with a unique four-wheel independent drive system, demonstrates excellent path-tracking capability and dynamic performance in agricultural environments. However, during actual field operations, issues such as severe tire slip, poor driving stability, high rollover risk, and excessive energy consumption often arise due to improper torque distribution. This study proposes an energy-efficient and stability-enhancing control method based on active torque distribution, aiming to improve both operational safety and system efficiency. A hierarchical control architecture is adopted: the upper-level controller employs a nonlinear model predictive control (NMPC) to achieve coordinated control of steering and yaw moment, enhancing lateral stability and ensuring operational safety. The lower-level controller implements a direct torque allocation method based on an adaptive-weight multi-objective twin delayed deep deterministic policy gradient (AW-MO-TD3) algorithm, enabling joint optimization of tire slip ratio and energy consumption. Real-vehicle tests were conducted under two typical field conditions, and the results show that compared with conventional methods, the proposed strategy significantly improves key performance metrics including tracking accuracy, vehicle stability, and energy efficiency. Specifically, stability was enhanced by 29.1 % and 41.4 %, while energy consumption was reduced by 19.8 % and 21.1 % under dry plowed terrain and muddy rice field conditions, respectively. This research provides technical support for the intelligent control of distributed drive electric agricultural vehicles.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 495-513"},"PeriodicalIF":12.4,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Two-year remote sensing and ground verification: Estimating chlorophyll content in winter wheat using UAV multi-spectral imagery 两年遥感与地面验证：利用无人机多光谱影像估算冬小麦叶绿素含量

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-05 DOI: 10.1016/j.aiia.2025.10.017

Wenjie Ai , Guofeng Yang , Zhongren Li , Jiawei Du , Lingzhen Ye , Xuping Feng , Xiangping Jin , Yong He

Leaf chlorophyll content serves as a critical biophysical indicator for characterizing wheat growth status. Traditional measurement using a SPAD meter, while convenient, is hampered by its localized sampling, low efficiency, and destructive nature, making it unsuitable for high-throughput field applications. To overcome these constraints, this research developed a novel approach for assessing canopy SPAD values in winter wheat by leveraging multispectral imagery obtained from an unmanned aerial vehicle (UAV). The generalizability of this methodology was rigorously evaluated through a replication experiment conducted in a subsequent growing season. Throughout the study, canopy reflectance data were acquired across key phenological stages and paired with synchronized ground-based SPAD measurements to construct stage-specific estimation models. The acquired multispectral images were processed to remove soil background interference, from which 17 distinct vegetation indices and 8 texture features were subsequently extracted. An in-depth examination followed, aiming to clarify the evolving interplay of these features with SPAD values throughout growth phases. Among the vegetation indices, the Modified Climate Change Canopy Vegetation Index (MCCCI) displayed a “rise-and-decline” pattern across the season, aligning with the crop's intrinsic growth dynamics and establishing it as a robust and phonologically interpretable proxy. Texture features, particularly contrast and entropy, demonstrated notable associations with SPAD values, reaching their peak strength during the booting stage. Comparative evaluation of various predictive modeling techniques revealed that a Support Vector Regression (SVR) model integrating both vegetation indices and texture features yielded the highest estimation accuracy. This integrated model outperformed models based solely on spectral or textural data, improving estimation accuracy by 23.81 % and 22.48 %, respectively. The model's strong generalization capability was further confirmed on the independent validation dataset from the second year (RMSE = 2.54, R² = 0.748). In summary, this study establishes an effective and transferable framework for non-destructively monitoring chlorophyll content in winter wheat canopies using UAV data.

叶片叶绿素含量是表征小麦生长状况的重要生物物理指标。使用SPAD仪表进行传统测量虽然方便，但由于其局部采样、低效率和破坏性，使其不适合高通量现场应用。为了克服这些限制，本研究开发了一种利用无人机（UAV）获得的多光谱图像来评估冬小麦冠层SPAD值的新方法。通过在随后的生长季节进行的重复实验，严格评估了该方法的普遍性。在整个研究过程中，获取了关键物候阶段的冠层反射率数据，并与同步的地面SPAD测量数据配对，构建了特定阶段的估算模型。对获取的多光谱图像进行去除土壤背景干扰的处理，提取出17种不同的植被指数和8种纹理特征。随后进行了深入的研究，旨在阐明这些特征在整个生长阶段与SPAD值之间不断变化的相互作用。在植被指数中，修正气候变化冠层植被指数（MCCCI）在整个季节中呈现出“上升-下降”的模式，与作物的内在生长动态一致，并建立了一个稳健的、可在音系上解释的指标。纹理特征，特别是对比度和熵，与SPAD值有显著的相关性，在启动阶段达到峰值。通过对各种预测建模技术的比较评估，发现结合植被指数和纹理特征的支持向量回归（SVR）模型的估计精度最高。该综合模型的估计精度分别提高了23.81%和22.48%，优于单纯基于光谱和纹理数据的模型。在第二年的独立验证数据集上进一步证实了模型较强的泛化能力（RMSE = 2.54, R2 = 0.748）。综上所述，本研究为利用无人机数据无损监测冬小麦冠层叶绿素含量建立了一个有效且可转移的框架。

{"title":"Two-year remote sensing and ground verification: Estimating chlorophyll content in winter wheat using UAV multi-spectral imagery","authors":"Wenjie Ai , Guofeng Yang , Zhongren Li , Jiawei Du , Lingzhen Ye , Xuping Feng , Xiangping Jin , Yong He","doi":"10.1016/j.aiia.2025.10.017","DOIUrl":"10.1016/j.aiia.2025.10.017","url":null,"abstract":"<div><div>Leaf chlorophyll content serves as a critical biophysical indicator for characterizing wheat growth status. Traditional measurement using a SPAD meter, while convenient, is hampered by its localized sampling, low efficiency, and destructive nature, making it unsuitable for high-throughput field applications. To overcome these constraints, this research developed a novel approach for assessing canopy SPAD values in winter wheat by leveraging multispectral imagery obtained from an unmanned aerial vehicle (UAV). The generalizability of this methodology was rigorously evaluated through a replication experiment conducted in a subsequent growing season. Throughout the study, canopy reflectance data were acquired across key phenological stages and paired with synchronized ground-based SPAD measurements to construct stage-specific estimation models. The acquired multispectral images were processed to remove soil background interference, from which 17 distinct vegetation indices and 8 texture features were subsequently extracted. An in-depth examination followed, aiming to clarify the evolving interplay of these features with SPAD values throughout growth phases. Among the vegetation indices, the Modified Climate Change Canopy Vegetation Index (MCCCI) displayed a “rise-and-decline” pattern across the season, aligning with the crop's intrinsic growth dynamics and establishing it as a robust and phonologically interpretable proxy. Texture features, particularly contrast and entropy, demonstrated notable associations with SPAD values, reaching their peak strength during the booting stage. Comparative evaluation of various predictive modeling techniques revealed that a Support Vector Regression (SVR) model integrating both vegetation indices and texture features yielded the highest estimation accuracy. This integrated model outperformed models based solely on spectral or textural data, improving estimation accuracy by 23.81 % and 22.48 %, respectively. The model's strong generalization capability was further confirmed on the independent validation dataset from the second year (RMSE = 2.54, R<sup>2</sup> = 0.748). In summary, this study establishes an effective and transferable framework for non-destructively monitoring chlorophyll content in winter wheat canopies using UAV data.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 480-494"},"PeriodicalIF":12.4,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decoupling tea-bud heap structure from non-imaging hyperspectral spectra for accurate single-bud trace biochemistry retrieval 将茶芽堆结构与非成像高光谱解耦，实现单芽微量生化精确检索

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-05 DOI: 10.1016/j.aiia.2025.11.003

Ning Qi , Hao Yang , Jianbo Qi , Wenjuan Li , Jinpeng Cheng , Xiaodong Yang , Bo Xu , Ze Xu , Guijun Yang , Chunjiang Zhao

Accurate, real-time, non-destructive estimation of single-bud biochemistry is critical for managing green-tea quality, yet non-imaging hyperspectral measurements of arbitrarily stacked buds are confounded by structured interference from mixed adaxial/abaxial surfaces and their three-dimensional arrangement. We propose Bilinear Spectral Derivative Gaussian Process Regression (BSDGPR), which couples a bilinear spectral-derivative model with Gaussian process regression to minimise structured interference. First- and second-order spectral derivatives attenuate the weakly wavelength-dependent leaf-spatial-arrangement term (R_LSA), while unit-sphere normalization combined with a chord-distance radial basis function kernel eliminate the plan-view leaf-front area fraction (f). This effectively standardizes tea-bud heap spectra to single-bud equivalents. (i) Structure suppression and invariance: independent-contribution analysis shows that moving to the derivative domain boosts the heap term's explanatory power to 80.7–99.4 % across bands while reducing R_LSA to ≤9.3 % (TH:LSA ratio of between 4.8 and 40.9), and the sphere-normalized chord-distance kernel cancels f-driven gain variation across samples. (ii) Accuracy and efficiency: relative to reflectance-domain GPR, BSDGPR raises R² by 0.13 and lowers NRMSE by 3–5 percentage points for tea polyphenols (0.68 → 0.81; 15.55 % → 12.64 %), amino acids (0.56 → 0.71; 19.78 % → 15.72 %), and soluble sugars (0.86 → 0.91; 10.85 % → 9.05 %), while maintaining fast inference (10–13 s per model) suitable for near real-time use. (iii) Transferability: models trained on tea-bud heaps generalize to canopy measurements with minimal loss (ΔR² ≤ 0.05; canopy NRMSE 11–15 %), remain credible across cultivars (R² = 0.37–0.74; NRMSE ≤23 % across 15 varieties), are stable at typical sensor resolutions (≤ 10–15 nm), and achieve R² = 0.63–0.66 with NRMSE ≤22 % for wheat canopy chlorophyll. Overall, BSDGPR is a reliable, field-ready AI approach for non-destructive biochemical sensing across crops, sensors, and management scenarios, offering broad applicability and strong potential for precision agriculture.

准确、实时、无损地估计单芽生物化学对于管理绿茶质量至关重要，然而，对任意堆叠的芽进行非成像高光谱测量会受到来自混合正面/背面及其三维排列的结构化干扰的干扰。我们提出了双线性谱导数高斯过程回归（BSDGPR），它将双线性谱导数模型与高斯过程回归相结合，以最小化结构干扰。一阶和二阶光谱导数可衰减波长依赖性较弱的叶片空间排列项（RLSA），而单位球归一化结合弦距径向基函数核可消除平面视图叶前面积分数(f)。这有效地将茶芽堆光谱标准化为单芽等效光谱。(i)结构抑制和不变性：独立贡献分析表明，移动到导数域将堆项的解释能力提高到80.7 - 99.4%，同时将RLSA降低到≤9.3% （TH:LSA比值在4.8 - 40.9之间），球归一化弦距核消除了样本间f驱动的增益变化。（ii）准确度和效率：相对于反射域GPR， BSDGPR对茶多酚（0.68→0.81;15.55%→12.64%）、氨基酸（0.56→0.71;19.78%→15.72%）和可溶性糖（0.86→0.91;10.85%→9.05%）的R2提高了0.13个百分点，NRMSE降低了3-5个百分点，同时保持了适合近实时使用的快速推断（每个模型10-13 s）。（iii）可转移性：在茶芽堆上训练的模型以最小的损失推广到冠层测量（ΔR2≤0.05；冠层NRMSE 11 - 15%），在不同品种间保持可信（R2 = 0.37-0.74； 15个品种间NRMSE≤23%），在典型传感器分辨率（≤10-15 nm）下保持稳定，在小麦冠层叶绿素NRMSE≤22%时达到R2 = 0.63-0.66。总体而言，BSDGPR是一种可靠的、现场准备的AI方法，可用于跨作物、传感器和管理场景的无损生化传感，为精准农业提供广泛的适用性和强大的潜力。

{"title":"Decoupling tea-bud heap structure from non-imaging hyperspectral spectra for accurate single-bud trace biochemistry retrieval","authors":"Ning Qi , Hao Yang , Jianbo Qi , Wenjuan Li , Jinpeng Cheng , Xiaodong Yang , Bo Xu , Ze Xu , Guijun Yang , Chunjiang Zhao","doi":"10.1016/j.aiia.2025.11.003","DOIUrl":"10.1016/j.aiia.2025.11.003","url":null,"abstract":"<div><div>Accurate, real-time, non-destructive estimation of single-bud biochemistry is critical for managing green-tea quality, yet non-imaging hyperspectral measurements of arbitrarily stacked buds are confounded by structured interference from mixed adaxial/abaxial surfaces and their three-dimensional arrangement. We propose Bilinear Spectral Derivative Gaussian Process Regression (BSDGPR), which couples a bilinear spectral-derivative model with Gaussian process regression to minimise structured interference. First- and second-order spectral derivatives attenuate the weakly wavelength-dependent leaf-spatial-arrangement term (<em>R</em><sub><em>LSA</em></sub>), while unit-sphere normalization combined with a chord-distance radial basis function kernel eliminate the plan-view leaf-front area fraction (<em>f</em>). This effectively standardizes tea-bud heap spectra to single-bud equivalents. (i) Structure suppression and invariance: independent-contribution analysis shows that moving to the derivative domain boosts the heap term's explanatory power to 80.7–99.4 % across bands while reducing <em>R</em><sub><em>LSA</em></sub> to ≤9.3 % (TH:LSA ratio of between 4.8 and 40.9), and the sphere-normalized chord-distance kernel cancels <em>f</em>-driven gain variation across samples. (ii) Accuracy and efficiency: relative to reflectance-domain GPR, BSDGPR raises R<sup>2</sup> by 0.13 and lowers NRMSE by 3–5 percentage points for tea polyphenols (0.68 → 0.81; 15.55 % → 12.64 %), amino acids (0.56 → 0.71; 19.78 % → 15.72 %), and soluble sugars (0.86 → 0.91; 10.85 % → 9.05 %), while maintaining fast inference (10–13 s per model) suitable for near real-time use. (iii) Transferability: models trained on tea-bud heaps generalize to canopy measurements with minimal loss (ΔR<sup>2</sup> ≤ 0.05; canopy NRMSE 11–15 %), remain credible across cultivars (R<sup>2</sup> = 0.37–0.74; NRMSE ≤23 % across 15 varieties), are stable at typical sensor resolutions (≤ 10–15 nm), and achieve R<sup>2</sup> = 0.63–0.66 with NRMSE ≤22 % for wheat canopy chlorophyll. Overall, BSDGPR is a reliable, field-ready AI approach for non-destructive biochemical sensing across crops, sensors, and management scenarios, offering broad applicability and strong potential for precision agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 397-411"},"PeriodicalIF":12.4,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

End-to-end detection of cough and snore based on ResNet18-TF for breeder laying hens: A field study 基于ResNet18-TF的种蛋鸡咳嗽和打鼾端到端检测的现场研究

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-04 DOI: 10.1016/j.aiia.2025.11.002

Haoyan Ma , Peiguang Xin , Juncheng Ma , Xiao Yang , Ruohan Zhang , Chao Liang , Yu Liu , Fei Qi , Chaoyuan Wang

Cough and snore are the most representative vocalizations for chicken respiratory diseases, which severely restrict poultry health due to highly contagious and lethal characteristics. Nighttime inspection by veterinarians is the foremost solution to identify bird respiratory symptoms during production. However, it is subjective, time-consuming, and labor-intensive. This study proposed a novel end-to-end model (ResNet18-TF) based on ResNet18 and a Time-Frequency Attention Mechanism (TFBlock) to automatically recognize chicken cough and snore using data collected in a commercial layer breeder house. In addition, a comparative analysis was conducted to evaluate the performance of different input features. The results revealed that LogFbank features exhibited superiority over MFCC features in the task of chicken sound recognition. By incorporating first-order and second-order delta features into LogFbank, the combination of ‘LogFbank+ΔLogFbank+ΔΔLogFbank’ further improved model recognition accuracy by 2.34 %. Additionally, the TFBlock structure enhanced the model's performance for recognizing coughs and snores. Specifically, the F1-score of MobileViTv3-TF, EfficientNetV2-TF, and ResNet18-TF models were increased by 1.30 %, 0.88 %, and 1.84 %, respectively, compared to their respective counterparts without TFBlock. ResNet18-TF achieved the highest accuracy, precision, recall, and F1-score, with 94.37 %, 94.59 %, 94.56 %, and 94.57 %, respectively. The generalization of ResNet18-TF in real production systems was validated, with precision and recall for detecting abnormal sounds (coughs and snores) reaching 92.97 % and 87.53 %, respectively. The proposed end-to-end model does not require denoising or endpoint detection processes, constructing an efficient and user-friendly pipeline of abnormal sound detection, which is highly suitable for practical deployment in poultry production systems.

咳嗽和打鼾是鸡呼吸道疾病最具代表性的发声方式，具有高度传染性和致死率，严重制约了家禽健康。兽医夜间检查是在生产过程中确定鸟类呼吸道症状的首要解决方案。然而，它是主观的、耗时的、劳动密集型的。本研究提出了一种基于ResNet18和时频注意机制（TFBlock）的端到端模型（ResNet18- tf），利用商业蛋鸡饲养场采集的数据自动识别鸡咳嗽和打鼾。此外，还对不同输入特征的性能进行了对比分析。结果表明，在鸡的声音识别任务中，LogFbank特征比MFCC特征表现出优越性。通过将一阶和二阶delta特征结合到LogFbank中，“LogFbank+ΔLogFbank+ΔΔLogFbank”的组合进一步提高了模型识别准确率2.34%。此外，TFBlock结构增强了模型识别咳嗽和打鼾的性能。其中，MobileViTv3-TF、EfficientNetV2-TF和ResNet18-TF模型的f1评分分别比未添加TFBlock的模型提高了1.30%、0.88%和1.84%。ResNet18-TF的准确率、精密度、召回率和f1得分最高，分别为94.37%、94.59%、94.56%和94.57%。在实际生产系统中验证了ResNet18-TF的泛化性，检测异常声音（咳嗽和打鼾）的准确率和召回率分别达到92.97%和87.53%。提出的端到端模型不需要去噪或端点检测过程，构建了一个高效且用户友好的异常声音检测管道，非常适合在家禽生产系统中实际部署。

{"title":"End-to-end detection of cough and snore based on ResNet18-TF for breeder laying hens: A field study","authors":"Haoyan Ma , Peiguang Xin , Juncheng Ma , Xiao Yang , Ruohan Zhang , Chao Liang , Yu Liu , Fei Qi , Chaoyuan Wang","doi":"10.1016/j.aiia.2025.11.002","DOIUrl":"10.1016/j.aiia.2025.11.002","url":null,"abstract":"<div><div>Cough and snore are the most representative vocalizations for chicken respiratory diseases, which severely restrict poultry health due to highly contagious and lethal characteristics. Nighttime inspection by veterinarians is the foremost solution to identify bird respiratory symptoms during production. However, it is subjective, time-consuming, and labor-intensive. This study proposed a novel end-to-end model (ResNet18-TF) based on ResNet18 and a Time-Frequency Attention Mechanism (TFBlock) to automatically recognize chicken cough and snore using data collected in a commercial layer breeder house. In addition, a comparative analysis was conducted to evaluate the performance of different input features. The results revealed that LogFbank features exhibited superiority over MFCC features in the task of chicken sound recognition. By incorporating first-order and second-order delta features into LogFbank, the combination of ‘LogFbank+ΔLogFbank+ΔΔLogFbank’ further improved model recognition accuracy by 2.34 %. Additionally, the TFBlock structure enhanced the model's performance for recognizing coughs and snores. Specifically, the F1-score of MobileViTv3-TF, EfficientNetV2-TF, and ResNet18-TF models were increased by 1.30 %, 0.88 %, and 1.84 %, respectively, compared to their respective counterparts without TFBlock. ResNet18-TF achieved the highest accuracy, precision, recall, and F1-score, with 94.37 %, 94.59 %, 94.56 %, and 94.57 %, respectively. The generalization of ResNet18-TF in real production systems was validated, with precision and recall for detecting abnormal sounds (coughs and snores) reaching 92.97 % and 87.53 %, respectively. The proposed end-to-end model does not require denoising or endpoint detection processes, constructing an efficient and user-friendly pipeline of abnormal sound detection, which is highly suitable for practical deployment in poultry production systems.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 412-422"},"PeriodicalIF":12.4,"publicationDate":"2025-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hyperspectral estimation of leaf chlorophyll content in wine grape using transfer learning and three-dimensional radiation transfer model 基于迁移学习和三维辐射迁移模型的高光谱估算酿酒葡萄叶片叶绿素含量

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-04 DOI: 10.1016/j.aiia.2025.11.001

Qifan Chen , Zhiwen Mi , Qifan Wang , Fahu Xu , Yulin Fang , Rui Wang , Yuyang Song , Baofeng Su

Accurate and timely monitoring of leaf chlorophyll content (LCC) in wine grapes is essential for assessing their photosynthetic status, optimizing management and planting practices, and improving both yield and quality. Traditional physically-based and empirically-based estimation methods often exhibit uncertainties, and they are inadequately adapted to nonlinear relationships. In this study, a UAV hyperspectral deep learning network (VitiChlNet) for estimating LCC of wine grapes was constructed. The estimation and mapping of LCC of wine grapes of different varieties and growth stages were realized by combining the three-dimensional radiation transfer model (3D RTM) and deep transfer learning (TL) techniques. Firstly, 80,000 canopy reflectance data under different canopy structures and observation conditions were simulated using the LESS model, the simulation dataset was then pre-trained using VitiChlNet. Finally, the model was fine-tuned using the TL technique based on the measured UAV hyperspectral and LCC data. The performance of VitiChlNet was compared to empirically-based and physically-based approaches. Specifically, three machine learning (ML) empirical models, XGBoost, LightGBM, and ridge regression, were developed using five different spectral feature construction strategies: full-spectrum, vegetation indices (VIs), competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE). Meanwhile, a look-up table (LUT) inversion strategy based on the LESS model was constructed. Furthermore, LCC mapping was conducted for various wine grape varieties across different growth stages. The results demonstrated that VitiChlNet outperformed other methods, exhibiting superior LCC estimation performance (R² = 0.69), and is less affected by factors such as nitrogen concentration and different interyears. The application of the TL technique enhanced LCC estimation accuracy and effectively addressed the small sample generalization problem. This study may provide a viable strategy for large-scale monitoring of LCC in wine grapes, which is of substantial significance for planting management practices.

准确、及时地监测酿酒葡萄叶片叶绿素含量（LCC），对评估酿酒葡萄的光合状态、优化管理和种植方式、提高产量和品质具有重要意义。传统的基于物理和经验的估计方法往往表现出不确定性，它们不能充分适应非线性关系。本文构建了用于酿酒葡萄LCC估计的无人机高光谱深度学习网络（VitiChlNet）。将三维辐射转移模型（3D RTM）与深度迁移学习（TL）技术相结合，实现了不同品种、不同生育期酿酒葡萄LCC的估算与制图。首先利用LESS模型对8万份不同冠层结构和观测条件下的冠层反射率数据进行模拟，然后利用VitiChlNet对模拟数据进行预训练。最后，基于实测的无人机高光谱和LCC数据，利用TL技术对模型进行微调。vitchlnet的性能与基于经验的方法和基于物理的方法进行了比较。具体而言，使用五种不同的光谱特征构建策略：全光谱、植被指数（VIs）、竞争自适应重加权采样（CARS）、逐次投影算法（SPA）和无信息变量消除（UVE），开发了XGBoost、LightGBM和ridge回归三种机器学习（ML）经验模型。同时，构造了基于LESS模型的查找表（LUT）反演策略。此外，还对不同酿酒葡萄品种在不同生长阶段进行了LCC制图。结果表明，vitchlnet的LCC估计性能优于其他方法（R2 = 0.69），且受氮浓度和年际差异等因素的影响较小。TL技术的应用提高了LCC估计的精度，有效地解决了小样本泛化问题。本研究为酿酒葡萄LCC的大规模监测提供了可行的策略，对种植管理实践具有重要意义。

{"title":"Hyperspectral estimation of leaf chlorophyll content in wine grape using transfer learning and three-dimensional radiation transfer model","authors":"Qifan Chen , Zhiwen Mi , Qifan Wang , Fahu Xu , Yulin Fang , Rui Wang , Yuyang Song , Baofeng Su","doi":"10.1016/j.aiia.2025.11.001","DOIUrl":"10.1016/j.aiia.2025.11.001","url":null,"abstract":"<div><div>Accurate and timely monitoring of leaf chlorophyll content (LCC) in wine grapes is essential for assessing their photosynthetic status, optimizing management and planting practices, and improving both yield and quality. Traditional physically-based and empirically-based estimation methods often exhibit uncertainties, and they are inadequately adapted to nonlinear relationships. In this study, a UAV hyperspectral deep learning network (VitiChlNet) for estimating LCC of wine grapes was constructed. The estimation and mapping of LCC of wine grapes of different varieties and growth stages were realized by combining the three-dimensional radiation transfer model (3D RTM) and deep transfer learning (TL) techniques. Firstly, 80,000 canopy reflectance data under different canopy structures and observation conditions were simulated using the LESS model, the simulation dataset was then pre-trained using VitiChlNet. Finally, the model was fine-tuned using the TL technique based on the measured UAV hyperspectral and LCC data. The performance of VitiChlNet was compared to empirically-based and physically-based approaches. Specifically, three machine learning (ML) empirical models, XGBoost, LightGBM, and ridge regression, were developed using five different spectral feature construction strategies: full-spectrum, vegetation indices (VIs), competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE). Meanwhile, a look-up table (LUT) inversion strategy based on the LESS model was constructed. Furthermore, LCC mapping was conducted for various wine grape varieties across different growth stages. The results demonstrated that VitiChlNet outperformed other methods, exhibiting superior LCC estimation performance (R<sup>2</sup> = 0.69), and is less affected by factors such as nitrogen concentration and different interyears. The application of the TL technique enhanced LCC estimation accuracy and effectively addressed the small sample generalization problem. This study may provide a viable strategy for large-scale monitoring of LCC in wine grapes, which is of substantial significance for planting management practices.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 423-438"},"PeriodicalIF":12.4,"publicationDate":"2025-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Organ3DNet: A deep network for segmenting organ semantics and instances from dense plant point clouds Organ3DNet：用于从密集植物点云中分割器官语义和实例的深度网络

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-11-03 DOI: 10.1016/j.aiia.2025.10.011

Dawei Li , Jiali Huang , Boyuan Zhao , Weiliang Wen

Worldwide food shortage has put the plant phenotyping research to the spotlight because phenotyping enhances crop yield under limited land use by accelerating the cycle of modern breeding. The prerequisite of organ-level phenotyping is the accurate segmentation of organs from crop point clouds. Though mainstream deep networks have reported satisfactory results on certain species, they usually require sampling each input point cloud to a fixed number before network learning. Most existing networks also recommend each input to contain less than 10,000 points, which may smooth the structural details and lead to deterioration of segmentation of small organs. Moreover, these methods are still struggling to face challenges such as segmenting crops with a large number of organs and scalability to multiple species. In this paper, we propose Organ3DNet—a novel deep-learning-based architecture tailored for organ segmentation on high-precision plant 3D data. By integrating a Sparse 3D Convolutional Network Backbone (S3DCNB) as encoder and a new Transformer Decoder part containing a cascade of Query Refinement Modules (QRM) and Mask Modules (MM), Organ3DNet begins with query points obtained with 3D Edge-preserving Sampling (3DEPS) and gradually refines those queries into masks to effectively represent different organ instances. A high-precision dataset containing 889 samples from five species is also provided in this study. In experiment on this dataset, our Organ3DNet outcompeted four networks including ASIS, JSNet, PlantNet, and PSegNet. On the organ semantic segmentation task, our method surpasses the second best JSNet by 2.10 % on F1 and 3.63 % on IoU; while on the instance segmentation task, Organ3DNet surpasses the second best PSegNet by large margins of 16.46 % on mCov and 13.44 % on mWCov, respectively. Validation tests also show that Organ3DNet performs well on downstream tasks and real agricultural scenarios. The dataset and code associated with Organ3DNet are open to the readers.

全球粮食短缺使植物表型研究成为人们关注的焦点，因为表型通过加快现代育种周期，在有限的土地利用下提高作物产量。器官水平表型的先决条件是准确分割器官从作物点云。尽管主流深度网络在某些物种上取得了令人满意的结果，但它们通常需要在网络学习之前对每个输入点云采样到固定的数量。大多数现有的网络还建议每个输入包含少于10,000个点，这可能会平滑结构细节，导致小器官的分割恶化。此外，这些方法仍然面临着诸如器官数量多的作物分割和多物种可扩展性等挑战。在本文中，我们提出了一种新的基于深度学习的架构organ3dnet，该架构专为高精度植物三维数据的器官分割而设计。通过集成稀疏三维卷积网络骨干（S3DCNB）作为编码器和包含查询细化模块（QRM）和掩码模块（MM）级联的新型变压器解码器，Organ3DNet从使用3D边缘保持采样（3DEPS）获得的查询点开始，逐步将这些查询细化为掩码，以有效地表示不同的器官实例。本研究还提供了一个包含5个物种889个样本的高精度数据集。在该数据集的实验中，我们的Organ3DNet打败了ASIS、JSNet、PlantNet和PSegNet四种网络。在器官语义分割任务上，我们的方法在F1和IoU上分别超过第二好的JSNet 2.10%和3.63%；而在实例分割任务上，Organ3DNet在mCov和mWCov上分别以16.46%和13.44%的优势大大超过了第二好的PSegNet。验证测试还表明，Organ3DNet在下游任务和实际农业场景中表现良好。与Organ3DNet相关的数据集和代码对读者开放。

{"title":"Organ3DNet: A deep network for segmenting organ semantics and instances from dense plant point clouds","authors":"Dawei Li , Jiali Huang , Boyuan Zhao , Weiliang Wen","doi":"10.1016/j.aiia.2025.10.011","DOIUrl":"10.1016/j.aiia.2025.10.011","url":null,"abstract":"<div><div>Worldwide food shortage has put the plant phenotyping research to the spotlight because phenotyping enhances crop yield under limited land use by accelerating the cycle of modern breeding. The prerequisite of organ-level phenotyping is the accurate segmentation of organs from crop point clouds. Though mainstream deep networks have reported satisfactory results on certain species, they usually require sampling each input point cloud to a fixed number before network learning. Most existing networks also recommend each input to contain less than 10,000 points, which may smooth the structural details and lead to deterioration of segmentation of small organs. Moreover, these methods are still struggling to face challenges such as segmenting crops with a large number of organs and scalability to multiple species. In this paper, we propose Organ3DNet—a novel deep-learning-based architecture tailored for organ segmentation on high-precision plant 3D data. By integrating a Sparse 3D Convolutional Network Backbone (S3DCNB) as encoder and a new Transformer Decoder part containing a cascade of Query Refinement Modules (QRM) and Mask Modules (MM), Organ3DNet begins with query points obtained with 3D Edge-preserving Sampling (3DEPS) and gradually refines those queries into masks to effectively represent different organ instances. A high-precision dataset containing 889 samples from five species is also provided in this study. In experiment on this dataset, our Organ3DNet outcompeted four networks including ASIS, JSNet, PlantNet, and PSegNet. On the organ semantic segmentation task, our method surpasses the second best JSNet by 2.10 % on F1 and 3.63 % on IoU; while on the instance segmentation task, Organ3DNet surpasses the second best PSegNet by large margins of 16.46 % on mCov and 13.44 % on mWCov, respectively. Validation tests also show that Organ3DNet performs well on downstream tasks and real agricultural scenarios. The dataset and code associated with Organ3DNet are open to the readers.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 342-364"},"PeriodicalIF":12.4,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0